Digital fishing field ecological chain intelligent scheduling system and method based on digital twinning

Abstract

The invention discloses a digital fishing field ecological chain intelligent scheduling system and method based on digital twinning, and relates to the technical field of digital twinning, and the method comprises the following steps: S1, arranging an Internet of Things sensor, and collecting a preliminary environment data set; s2, in combination with a Kalman filter algorithm, constructing and updating a digital twin virtual model in real time; s3, calculating a resource consumption index, and generating a resource scheduling optimization scheme in combination with a conjugate gradient algorithm; s4, performing dynamic simulation, and generating a resource scheduling implementation scheme in combination with an ecological assessment result; and S5, calculating a resource scheduling adjustment amount according to a feedback control algorithm, and generating a resource scheduling adjustment effect report in combination with an adjustment result. According to the method, the digital twinborn technology, the conjugate gradient algorithm and the feedback control algorithm are combined, intelligent scheduling of fishing field resources is achieved, and the method has the advantages of being high in real-time performance, high in intelligent degree and fast in data processing.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology, and in particular to a digital fishing ground ecosystem intelligent scheduling system and method based on digital twins. Background Technology

[0002] As modern fishing grounds continue to expand, their management faces challenges in resource allocation, ecological protection, and customer experience. Traditional fishing ground management methods often rely on manual experience, failing to respond in real-time to changes in the ecological environment and leaving significant room for optimization in resource allocation. Most fishing ground management systems depend on traditional information management systems, which lack interaction with real-time data and fail to effectively integrate environmental monitoring with resource allocation. Resource allocation at fishing grounds, including fishing spots, tackle, and personnel, is often based on experience, making precise resource allocation and optimal utilization difficult.

[0003] To address these issues, digital twin technology is gradually gaining popularity in the field of fishing ground management. In fishing ground management, digital twin technology can construct a virtual model synchronized with the actual fishing ground by monitoring environmental and ecological data in real time, thereby enabling intelligent scheduling and resource optimization of the fishing ground.

[0004] While existing technological solutions have addressed the issues of fishing ground resource allocation and ecological management to some extent, shortcomings remain in areas such as real-time performance, intelligence, and data processing. First, most existing systems cannot respond in real-time to changes in fishing ground resources and the ecological environment, especially in the event of emergencies or environmental fluctuations, failing to dynamically adjust allocation plans and exhibiting poor real-time performance. Second, although some systems utilize optimization algorithms and simulation techniques for resource allocation, they often focus solely on resource optimization, neglecting ecological protection needs and failing to achieve comprehensive multi-dimensional optimization. Furthermore, while current IoT-based fishing ground management systems provide real-time monitoring for data collection, they lack robust support in data processing and integration, making it difficult to transform data into practical decision support. They also lack effective data analysis and fusion processing mechanisms, exhibiting limited data processing capabilities.

[0005] Therefore, how to provide a digital twin-based intelligent scheduling system and method for the digital fishing ecosystem is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] One objective of this invention is to provide a digital twin-based intelligent scheduling system and method for the digital fishing ground ecosystem. This invention combines digital twin technology, conjugate gradient optimization algorithm, and feedback control algorithm to monitor changes in the fishing ground's ecological environment in real time and accurately schedule fishing ground resources. This method can improve the efficiency of resource allocation, ensure the sustainability of the ecological environment, provide intelligent decision support, enhance the flexibility and responsiveness of fishing ground management, improve the economic and ecological benefits of the fishing ground, and avoid the problems of unreasonable resource allocation, insufficient ecological management, and delayed response found in traditional fishing ground resource scheduling methods, thus achieving the optimal balance between resource optimization, ecological protection, and economic benefits.

[0007] The intelligent scheduling method for the digital fishing ground ecosystem based on digital twins according to embodiments of the present invention includes the following steps: S1. Deploy IoT sensors to collect environmental data in real time and perform data fusion to generate a preliminary environmental dataset; S2. Based on the preliminary environmental dataset, label the time series data, and combine the Kalman filter algorithm to construct and update the digital twin virtual model in real time; S3. Based on the digital twin virtual model, calculate the resource consumption index, set the resource scheduling optimization objective function, and generate a resource scheduling optimization scheme by combining the optimization results of the conjugate gradient algorithm. S4. Based on the resource scheduling optimization plan, use a digital twin virtual model to perform dynamic simulation, conduct an ecological assessment based on the simulation results, and generate a resource scheduling implementation plan based on the ecological assessment results. S5. Execute the resource scheduling implementation plan, collect resource assessment data, combine feedback control algorithms to calculate resource scheduling adjustment amounts, formulate and implement resource scheduling adjustment plans, analyze the adjusted resource assessment data, and generate a resource scheduling adjustment effect report.

[0008] Optionally, S1 specifically includes: S11. Deploy IoT sensors in the fishing area to collect environmental data in real time. The IoT sensors include water quality sensors, temperature and humidity sensors, fish activity sensors, visitor flow sensors, and geographic information sensors. S12. The water quality sensor is used to collect water quality data in real time, including pH value, dissolved oxygen concentration, turbidity, ammonia nitrogen content and water temperature; S13. The temperature and humidity sensor is used to collect meteorological data in real time, including air temperature, humidity and air pressure; S14. The fish activity sensor is used to collect fish data in real time, including the distribution of the fish, the population size, the activity range and the movement speed. S15. The passenger flow sensor is used to collect passenger flow data in real time, including customer entry time, fishing area, stay time, and fishing activity type. S16. The geographic information sensor is used to collect geographic information data in real time, including geographic coordinates, water depth, land area, altitude, and slope; S17. The environmental data is fused to generate a preliminary environmental dataset, which includes water quality data, meteorological data, fish population data, passenger flow data, and geographic information data.

[0009] Optionally, S2 specifically includes: S21. Based on the preliminary environmental dataset, and in conjunction with the 3D modeling software AutoCAD, a 3D model of the fishing ground is constructed to build a digital twin virtual model containing data on the fishing area, fish activity area, water environment, and facility layout. S22. Based on the digital twin virtual model, environmental data is marked and updated in real time; S23. Based on environmental data, timestamp the data according to the time sequence to obtain time series data, and use Redis database to record and update it; S24. Using the Kalman filter algorithm, the real-time collected environmental data and time series data are accurately synchronized to update the digital twin virtual model.

[0010] Optionally, S3 specifically includes: S31. Based on the digital twin virtual model, extract the resource usage data of the fishing area, including dissolved oxygen concentration, water temperature, fish density, facility occupancy rate, facility usage frequency and visitor flow for each fishing area; S32. Based on the fishing ground resource usage data, calculate the resource consumption indicators, including resource utilization, resource consumption amount, and resource consumption rate. S33. Based on resource consumption indicators, set the objective function for resource scheduling optimization:

[0011] Where Z is the objective function for resource scheduling optimization. For the first Regional resource utilization For the first The rate of resource consumption in the region For the first Fish density in the area For the first The dissolved oxygen concentration in the water of the area For the first The temperature of the region These are the weighting coefficients for each objective. The number of fishing areas; S34. Calculate the initial gradient based on the resource scheduling optimization objective function: ; in, For the initial gradient, To optimize the objective function for resource scheduling, It is the partial derivative of the resource scheduling optimization objective function with respect to the i-th decision variable, each The resource allocation variables representing the i-th region include the fish stocking quantity and the fishing area allocation quantity; S35. Calculate the initial search direction based on the initial gradient: in, As the initial search direction, This is the initial gradient; S36. Based on the initial search direction, calculate the step size after iteration by minimizing the projection of the objective function onto the current search direction: in, It is the step size after iteration. It is the projection of the objective function onto the current solution along the search direction. The initial step size, To optimize the objective function for resource scheduling, This is the initial solution for the resource scheduling scheme. This is the initial search direction; S37. Based on the search direction and the step size after iteration, adjust the resource allocation, fish stocking, fishing area arrangement, and facility usage decisions for the fishing area, and update the resource scheduling optimization objective function. S38. Calculate the new gradient based on the resource scheduling optimization objective function, and determine whether the optimization convergence condition is met. If the change in the objective function value is less than the preset threshold, or the gradient is close enough to zero, the optimization is considered to have converged and the iteration is exited; otherwise, the next round of optimization iteration is performed. S39. Based on the iteration results, generate a resource scheduling optimization scheme.

[0012] Optionally, S4 specifically includes: S41. Based on the resource scheduling optimization scheme, perform dynamic simulation to obtain simulated environmental data, including water quality data, meteorological data, fish population data, passenger flow data, and geographic information data. S42. Calculate the predicted resource consumption based on the simulated environment data; S43. Calculate the ecological impact value based on the predicted resource consumption:

[0013] in, For the first The ecological impact value of the region For fish density, Dissolved oxygen concentration in water. Forecast of resource consumption These are the weighting coefficients; S44. Based on the ecological impact value, compare the simulated environmental data and the actual environmental data, analyze and generate a simulation report, including resource usage, consumption prediction, ecological impact assessment opinions, and resource scheduling adjustment suggestions; S45. Based on the simulation report, adjust the resource allocation of the fishing ground and generate a resource scheduling implementation plan, including resource allocation, fish stocking quantity, fishing area arrangement and facility resource allocation for each fishing area.

[0014] Optionally, S5 specifically includes: S51. Execute the resource scheduling implementation plan and collect resource assessment data in real time, including dissolved oxygen concentration, water temperature, fish density, visitor flow, and facility usage status. S52. Based on resource assessment data and feedback control algorithms, calculate the resource scheduling adjustment amount:

[0015] in, For the first Regional resource scheduling adjustment and For the first Current and target fish density in the area. and The current and target dissolved oxygen concentrations, and For current and target passenger flow, These are the weighting coefficients; S53. Based on the resource allocation adjustment amount, formulate a resource allocation adjustment plan, including fish stocking quantity, regional allocation and facility resource use; S54. Implement the resource scheduling and adjustment plan, collect resource assessment data in real time, record and analyze the resource assessment data, and generate a resource scheduling and adjustment effect report, including resource assessment data, ecological indicator data, ecological impact assessment opinions, and resource scheduling and adjustment suggestions.

[0016] The intelligent scheduling system for the digital fishing ground ecosystem based on digital twins includes the following modules: IoT sensor modules are used to collect real-time environmental data of the fishing grounds. The digital twin module is used to build and update a digital twin virtual model of the fishing ground in real time. The data analysis and algorithm optimization module is used to analyze the resource usage data of the fishing grounds in the digital twin virtual model and generate resource scheduling optimization schemes by combining the conjugate gradient algorithm. The simulation and ecological assessment module is used to perform dynamic simulation of resource scheduling optimization schemes and generate resource scheduling optimization schemes by combining the conjugate gradient algorithm. The feedback control module is used to dynamically adjust and optimize the allocation of fishing ground resources in conjunction with a feedback control algorithm. The beneficial effects of this invention are:

[0017] First, this invention successfully solves the problems of inaccurate resource allocation, insufficient ecological protection, and delayed response in traditional fishing ground management by combining digital twin technology with intelligent scheduling algorithms. Traditional fishing ground management often relies on manual operation, making it difficult to make rapid decisions based on real-time data, resulting in inaccurate resource scheduling and a certain lag in ecological protection. Digital twin technology, by constructing and updating a virtual model in real time, can accurately reflect the real-time status of the fishing ground, including water quality, temperature, and fish distribution. Furthermore, the intelligent scheduling algorithm can dynamically adjust based on this real-time data, not only improving the accuracy of scheduling but also responding quickly to changes in the environment, resource consumption, and ecological impact. This combination of technologies enables fishing grounds to flexibly respond to different changes, ensuring optimal resource allocation, achieving precise resource scheduling and management, and thus significantly improving the operational efficiency of the fishing grounds.

[0018] Secondly, this invention combines the conjugate gradient algorithm to achieve efficient scheduling and optimized allocation of fishing resources. The conjugate gradient algorithm is a highly efficient algorithm for optimizing large-scale problems, capable of obtaining the optimal resource allocation scheme while ensuring computational efficiency. Through continuous optimization of the algorithm, the system can automatically adjust the allocation of fishing spots, the use of fishing gear, and the deployment of staff based on real-time collected data. These decisions not only ensure the rational use of fishing resources and improve resource utilization, avoiding over-exploitation, but also optimize the visitor experience. Through this intelligent scheduling, the fishing ground can rationally allocate various resources according to actual needs and environmental changes, reducing human intervention and resource waste, improving operational efficiency, and maximizing the satisfaction of visitor needs.

[0019] Then, this invention provides in-depth analysis and optimization decision support for resource allocation schemes through multi-dimensional ecological impact assessment. Resource allocation in fishing grounds needs to consider not only economic benefits but also the impact on the ecological environment. To ensure ecological balance, the system comprehensively evaluates real-time data from multiple dimensions, including water quality, meteorological data, and fish distribution, forming a complete ecological assessment mechanism. Through ecological assessment, the potential negative impacts of resource consumption on the ecological environment can be accurately identified, and resource allocation schemes can be adjusted based on the assessment results, thereby avoiding excessive resource consumption and ecological damage. This ensures that while improving the economic benefits of fishing grounds, the ecological environment can also be effectively protected, promoting an eco-friendly fishing ground management model.

[0020] Finally, this invention combines real-time data feedback and a dynamic adjustment mechanism to continuously optimize resource allocation schemes by recording and analyzing the effects of each adjustment. Fishing ground management is a dynamic process; as environmental conditions change, resource allocation also needs constant adjustment. Through real-time data feedback, the system can continuously monitor the fishing ground's status, promptly identify problems, and make corresponding adjustments. Combined with a feedback control algorithm, the system will self-optimize based on the effects of each adjustment, continuously improving the accuracy and efficiency of resource allocation. This continuous optimization mechanism enables the fishing ground to maintain optimal resource allocation in a constantly changing environment, ensuring that it can effectively maintain ecological balance while pursuing economic benefits. Through this dynamic adjustment, the fishing ground not only improves operational efficiency but also provides scientific support for its long-term development, ensuring the sustainable development of the fishing ground. Attached Figure Description

[0021] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0022] Figure 1 This is an overall flowchart of the intelligent scheduling system and method for the digital fishing ground ecosystem based on digital twins proposed in this invention; Figure 2 The diagram shows the calculation process of the conjugate gradient algorithm for the intelligent scheduling system and method for the digital fishing ground ecosystem based on digital twins proposed in this invention. Detailed Implementation

[0023] The invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0024] refer to Figure 1-2 The intelligent scheduling method for the digital fishing ground ecosystem based on digital twins includes the following steps: S1. Deploy IoT sensors to collect environmental data in real time and perform data fusion to generate a preliminary environmental dataset; S2. Based on the preliminary environmental dataset, label the time series data, and combine the Kalman filter algorithm to construct and update the digital twin virtual model in real time; S3. Based on the digital twin virtual model, calculate the resource consumption index, set the resource scheduling optimization objective function, and generate a resource scheduling optimization scheme by combining the optimization results of the conjugate gradient algorithm. S4. Based on the resource scheduling optimization plan, use a digital twin virtual model to perform dynamic simulation, conduct an ecological assessment based on the simulation results, and generate a resource scheduling implementation plan based on the ecological assessment results. S5. Execute the resource scheduling implementation plan, collect resource assessment data, combine feedback control algorithms to calculate resource scheduling adjustment amounts, formulate and implement resource scheduling adjustment plans, analyze the adjusted resource assessment data, and generate a resource scheduling adjustment effect report. In this embodiment, S1 specifically includes: S11. Deploy IoT sensors in the fishing area to collect environmental data in real time. The IoT sensors include water quality sensors, temperature and humidity sensors, fish activity sensors, visitor flow sensors, and geographic information sensors. S12. The water quality sensor is used to collect water quality data in real time, including pH value, dissolved oxygen concentration, turbidity, ammonia nitrogen content and water temperature; S13. The temperature and humidity sensor is used to collect meteorological data in real time, including air temperature, humidity and air pressure; S14. The fish activity sensor is used to collect fish data in real time, including the distribution of the fish, the population size, the activity range and the movement speed. S15. The passenger flow sensor is used to collect passenger flow data in real time, including customer entry time, fishing area, stay time, and fishing activity type. S16. The geographic information sensor is used to collect geographic information data in real time, including geographic coordinates, water depth, land area, altitude, and slope; S17. The environmental data is fused to generate a preliminary environmental dataset, which includes water quality data, meteorological data, fish population data, passenger flow data, and geographic information data.

[0025] In this embodiment, S2 specifically includes: S21. Based on the preliminary environmental dataset, and in conjunction with the 3D modeling software AutoCAD, a 3D model of the fishing ground is constructed to build a digital twin virtual model containing data on the fishing area, fish activity area, water environment, and facility layout. S22. Based on the digital twin virtual model, environmental data is marked and updated in real time; S23. Based on environmental data, timestamp the data according to the time sequence to obtain time series data, and use Redis database to record and update it; S24. Using the Kalman filter algorithm, the real-time collected environmental data and time series data are accurately synchronized to update the digital twin virtual model.

[0026] In this embodiment, S3 specifically includes: S31. Based on the digital twin virtual model, extract the resource usage data of the fishing area, including dissolved oxygen concentration, water temperature, fish density, facility occupancy rate, facility usage frequency and visitor flow for each fishing area; S32. Based on the fishing ground resource usage data, calculate the resource consumption indicators, including resource utilization, resource consumption amount, and resource consumption rate. S33. Based on resource consumption indicators, set the objective function for resource scheduling optimization:

[0027] Where Z is the objective function for resource scheduling optimization. For the first Regional resource utilization For the first The rate of resource consumption in the region For the first Fish density in the area For the first The dissolved oxygen concentration in the water of the area For the first The temperature of the region These are the weighting coefficients for each objective. The number of fishing areas; S34. Calculate the initial gradient based on the resource scheduling optimization objective function: ; in, For the initial gradient, To optimize the objective function for resource scheduling, It is the partial derivative of the resource scheduling optimization objective function with respect to the i-th decision variable, each The resource allocation variables representing the i-th region include the fish stocking quantity and the fishing area allocation quantity; S35. Calculate the initial search direction based on the initial gradient: in, As the initial search direction, This is the initial gradient; S36. Based on the initial search direction, calculate the step size after iteration by minimizing the projection of the objective function onto the current search direction: in, It is the step size after iteration. It is the projection of the objective function onto the current solution along the search direction. The initial step size, To optimize the objective function for resource scheduling, This is the initial solution for the resource scheduling scheme. This is the initial search direction; S37. Based on the search direction and the step size after iteration, adjust the resource allocation, fish stocking, fishing area arrangement, and facility usage decisions for the fishing area, and update the resource scheduling optimization objective function. S38. Calculate the new gradient based on the resource scheduling optimization objective function, and determine whether the optimization convergence condition is met. If the change in the objective function value is less than the preset threshold, or the gradient is close enough to zero, the optimization is considered to have converged and the iteration is exited. Otherwise, jump to S36 for the next round of optimization iteration. S39. Based on the iteration results, generate a resource scheduling optimization scheme.

[0028] In this embodiment, S4 specifically includes: S41. Based on the resource scheduling optimization scheme, perform dynamic simulation to obtain simulated environmental data, including water quality data, meteorological data, fish population data, passenger flow data, and geographic information data. S42. Calculate the predicted resource consumption based on the simulated environment data; S43. Calculate the ecological impact value based on the predicted resource consumption:

[0029] in, For the first The ecological impact value of the region For fish density, Dissolved oxygen concentration in water. Forecast of resource consumption These are the weighting coefficients; S44. Based on the ecological impact value, compare the simulated environmental data and the actual environmental data, analyze and generate a simulation report, including resource usage, consumption prediction, ecological impact assessment opinions, and resource scheduling adjustment suggestions; S45. Based on the simulation report, adjust the resource allocation of the fishing ground and generate a resource scheduling implementation plan, including resource allocation, fish stocking quantity, fishing area arrangement and facility resource allocation for each fishing area.

[0030] In this embodiment, S5 specifically includes: S51. Execute the resource scheduling implementation plan and collect resource assessment data in real time, including dissolved oxygen concentration, water temperature, fish density, visitor flow, and facility usage status. S52. Based on resource assessment data and feedback control algorithms, calculate the resource scheduling adjustment amount:

[0031] in, For the first Regional resource scheduling adjustment and For the first Current and target fish density in the area. and The current and target dissolved oxygen concentrations, and For current and target passenger flow, These are the weighting coefficients; S53. Based on the resource allocation adjustment amount, formulate a resource allocation adjustment plan, including fish stocking quantity, regional allocation and facility resource use; S54. Implement the resource scheduling and adjustment plan, collect resource assessment data in real time, record and analyze the resource assessment data, and generate a resource scheduling and adjustment effect report, including resource assessment data, ecological indicator data, ecological impact assessment opinions, and resource scheduling and adjustment suggestions.

[0032] refer to Figure 1 The intelligent scheduling system for the digital fishing ground ecosystem based on digital twins includes the following modules: IoT sensor modules are used to collect real-time environmental data of the fishing grounds. The digital twin module is used to build and update a digital twin virtual model of the fishing ground in real time. The data analysis and algorithm optimization module is used to analyze the resource usage data of the fishing grounds in the digital twin virtual model and generate resource scheduling optimization schemes by combining the conjugate gradient algorithm. The simulation and ecological assessment module is used to dynamically simulate resource scheduling optimization schemes and generate resource scheduling implementation schemes by combining ecological assessment results. The feedback control module is used to dynamically adjust and optimize the allocation of fishing ground resources by combining feedback control algorithms.

[0033] Example 1: To verify the feasibility of this invention in practice, it was applied to a large fishing ground (hereinafter referred to as "Fishing Ground A"). This fishing ground primarily provides recreational activities, fishing services, and ecological protection, but its management and resource allocation face many challenges, including fluctuations in visitor flow, fish health, and the balance of the ecological environment. Traditional resource allocation methods rely mainly on experience and fixed rules, which cannot cope with the dynamic demands of changing visitor flow and environment, leading to resource waste and ecological impact. To improve resource allocation efficiency and optimize fishing ground management, Fishing Ground A decided to adopt the intelligent scheduling system and method for the digital fishing ground ecosystem based on digital twins proposed in this invention.

[0034] During implementation, fishing ground A uses installed IoT sensors to collect real-time environmental data, including water quality data (pH, dissolved oxygen concentration, turbidity, ammonia nitrogen content, water temperature), meteorological data (air temperature, humidity, air pressure), fish data (distribution, population size, activity range, and movement speed), visitor traffic data (entry time, fishing area, stay time, and type of fishing activity), and facility usage. The collected environmental data undergoes standardized processing, including format unification, noise reduction, and missing value completion, to ensure accuracy and completeness. All data is organized chronologically and used for subsequent resource scheduling and optimization.

[0035] After obtaining environmental data, fishing site A uses digital twin technology to construct a digital twin virtual model based on real-time environmental monitoring data, simulating the actual state of the fishing site. By comparing it with real-time data from the physical fishing site, the digital twin virtual model can accurately reflect the resource utilization of the fishing site. Fishing site A uses the digital twin to analyze the resource utilization of each fishing area and assess the rationality of the current resource allocation.

[0036] After establishing a digital twin virtual model, fishing ground A uses an improved conjugate gradient algorithm to optimize resource scheduling. First, an objective function for resource scheduling is established, considering various constraints of the fishing ground, including area capacity, fish density, and visitor flow. Then, based on current resource consumption indicators, including resource utilization, resource consumption amount, and resource consumption rate, the optimal resource scheduling scheme is calculated using the conjugate gradient algorithm to optimize the objective function and ensure optimal resource allocation.

[0037] After the target resource allocation plan is calculated, the scheduling control system of fishing site A automatically generates scheduling instructions to adjust the stocking density of fish, area allocation, and facility resource usage in the fishing area. These control instructions are executed through the automated scheduling system, which monitors the resource allocation effect in real time. Once a deviation between the resource allocation and the target value is detected, the system will automatically adjust to ensure that the resource allocation is always in an optimal state.

[0038] During implementation, the managers of fishing ground A observed that, compared to traditional scheduling methods, the intelligent scheduling system and method based on digital twins for the digital fishing ground ecosystem significantly improved resource utilization efficiency and management accuracy. In traditional methods, fishing grounds often experience resource waste or ecological impact due to their inability to respond promptly to environmental changes or fluctuations in visitor traffic. However, with the application of this invention, the resource scheduling of the fishing ground is consistently maintained at an optimal level. Fishing ground A can quickly adjust resource allocation in the face of emergencies such as fluctuations in visitor traffic and weather changes, avoiding resource waste or ecological damage.

[0039] To further verify the effectiveness of this method, data was compared with that obtained using traditional water level control methods. The comparison table is as follows: Table 1 Comparison Data of Fishing Ground A Intelligent Dispatch System

[0040] As shown in Table 1, the application of the method of this invention significantly improves the resource allocation efficiency of fishing grounds. The utilization rate of fishing spots increased from 72% under the traditional method to 91%, the utilization rate of fishing gear increased from 65% to 85%, staff arrangements became more efficient, and visitor waiting time decreased by 30%. Simultaneously, the ecological environment of the fishing grounds was effectively protected, water quality stability improved by 15%, the natural activity of fish was preserved, and ecological imbalance caused by overfishing was avoided. Furthermore, overall visitor satisfaction also increased significantly, from 78% to 90%, and the problem-solving rate improved by 20%.

[0041] Furthermore, traditional methods cannot cope with sudden changes and complex environmental conditions, while the method of this invention, through real-time data collection and intelligent decision support, can flexibly respond to environmental changes, ensuring that the fishing grounds can optimize resource allocation while protecting the ecological environment, ultimately achieving a win-win situation for both economic and ecological benefits.

[0042] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A digitalized fishing ground ecological chain intelligent scheduling method based on digital twinning, characterized in that, Comprise the following steps: S1, layout Internet of Things sensor, real-time collection of environmental data and data fusion, generate preliminary environmental data set; S2, according to the preliminary environmental data set, mark time series data, combined with Kalman filter algorithm, build and real-time update digital twin virtual model; S3, according to the digital twin virtual model, calculate the resource consumption index, and set the resource scheduling optimization objective function, combine the conjugate gradient algorithm to optimize the result, generate resource scheduling optimization scheme; S4, according to the resource scheduling optimization scheme, using digital twin virtual model for dynamic simulation, based on the simulation results of ecological evaluation, combined with the ecological evaluation results to generate resource scheduling implementation scheme; S5, execute resource scheduling implementation scheme, collect resource evaluation data, combined with feedback control algorithm, calculate resource scheduling adjustment, and formulate and implement resource scheduling adjustment scheme, analyze the resource evaluation data after adjustment, generate resource scheduling adjustment effect report.

2. The digital twin-based digital fishing ground ecological chain intelligent scheduling method according to claim 1, characterized in that, The S1 comprises the following steps: S11, layout Internet of Things sensor in the fishing ground, real-time collection of environmental data, the Internet of Things sensor includes water quality sensor, temperature and humidity sensor, fish activity sensor, passenger flow sensor and geographic information sensor; S12, the water quality sensor is used for real-time collection of water quality data, including pH, dissolved oxygen concentration, turbidity, ammonia nitrogen content and water temperature; S13, the temperature and humidity sensor is used for real-time collection of meteorological data, including air temperature, humidity and air pressure; S14, the fish activity sensor is used for real-time collection of fish data, including the distribution of fish population, population number, activity range and moving speed; S15, the passenger flow sensor is used for real-time collection of passenger flow data, including customer entry time, fishing area, stay time, fishing activity type; S16, the geographic information sensor is used for real-time collection of geographic information data, including geographic coordinates, water depth, land area, elevation, slope; S17, the environmental data is fused to generate preliminary environmental data set, the preliminary environmental data set includes water quality data, meteorological data, fish data, passenger flow data, geographic information data.

3. The digital twin-based digital fishing ground ecosystem chain intelligent scheduling method according to claim 1, characterized in that, The S2 comprises the following steps: S21, according to the preliminary environmental data set, combined with three-dimensional modeling software AutoCAD, three-dimensional modeling of fishing ground, build digital twin virtual model containing fishing area, fish activity area, water environment, facility layout data; S22, based on digital twin virtual model, real-time mark and update environmental data; S23, based on environmental data, time stamp labeling in time sequence, get time series data, and use Redis database record and update; S24, using Kalman filter algorithm, accurate synchronization of real-time collected environmental data and time series data, update digital twin virtual model.

4. The digital twin-based digital fishing ground ecological chain intelligent scheduling method according to claim 1, characterized in that, The S3 comprises the following steps: S31, according to the digital twin virtual model, extract fishing ground resource use data, including dissolved oxygen concentration, water temperature, fish density, facility occupancy rate, facility use frequency and passenger flow of each fishing area; S32, calculate resource consumption indicators including resource utilization, resource consumption, and resource consumption rate according to the fishing field resource use data; S33、according to the resource consumption index, set a resource scheduling optimization objective function:

5. wherein, Z is the objective function for resource scheduling optimization. For the first Regional resource utilization For the first The rate of resource consumption in the region For the first Fish density in the area For the first The dissolved oxygen concentration in the water of the area For the first The temperature of the region These are the weighting coefficients for each objective. The number of fishing areas; S34, calculate an initial gradient according to the resource scheduling optimization objective function; ； wherein, is an initial gradient, is a resource scheduling optimization objective function, is a partial derivative of the resource scheduling optimization objective function with respect to the i-th decision variable, each represents a resource configuration variable of the i-th region, including the amount of fish stocking and the amount of fishing area allocation; S35. Calculate an initial search direction based on the initial gradient: wherein, is the initial search direction, is the initial gradient; S36、According to the initial search direction, the step after iteration is calculated by minimizing the projection of the objective function on the current search direction: wherein, is the step after iteration, is the projection of the objective function along the search direction in the current solution, is the initial step, is the resource scheduling optimization objective function, is the initial solution of the resource scheduling scheme, is the initial search direction; S37, adjust the resource allocation amount of the fishing area, the fish stocking amount, the fishing area arrangement, and the facility use decision according to the search direction and the iterated step length, and update the resource scheduling optimization objective function; S38, calculate a new gradient according to the resource scheduling optimization objective function, and determine whether the optimization convergence condition is met. If the change in the objective function value is less than a preset threshold, or the gradient is close enough to zero, it is considered that the optimization converges, the iteration is exited, otherwise the next round of optimization iteration is performed; S39, generate a resource scheduling optimization scheme according to the iteration result.

6. The digital twin-based digital fishing ground ecosystem chain intelligent scheduling method according to claim 1, characterized in that, The S5 includes the following steps: S41, based on the resource scheduling optimization scheme, perform dynamic simulation to obtain simulation environment data including water quality data, weather data, fish population data, passenger flow data, and geographic information data; S42, calculate resource consumption prediction according to the simulation environment data; S43. Calculate the ecological impact value according to the resource consumption prediction:

7. wherein, is the first ecological impact value of the region, is the fish density, is the water quality dissolved oxygen concentration, is the resource consumption prediction, is the weight coefficient; S44, based on the ecological impact value, compare the simulation environment data and the actual environment data, analyze and generate a simulation report including resource use, consumption prediction, ecological impact assessment, and resource scheduling adjustment suggestions; S45, according to the simulation report, adjust the fishing field resource configuration, and generate a resource scheduling implementation scheme including resource allocation, fish stocking amount, fishing area arrangement, and facility resource configuration for each fishing area.

8. The digital twin-based digital fishing ground ecosystem chain intelligent scheduling method according to claim 1, characterized in that, The S8 includes the following steps: S51, execute the resource scheduling implementation scheme, and collect resource evaluation data including dissolved oxygen concentration, water temperature, fish population density, passenger flow, and facility use status in real time; S52、According to the resource evaluation data, combining the feedback control algorithm, calculate the resource scheduling adjustment amount:

9. wherein, For the first The resource scheduling adjustment amount of the region And For the first The current and target fish density of the region, And The current and target dissolved oxygen concentration, And The current and target passenger flow, Is the weight coefficient; S53, develop a resource scheduling adjustment scheme including fish stocking amount, area allocation, and facility resource use according to the resource scheduling adjustment amount; S54, execute the resource scheduling adjustment scheme, collect resource evaluation data in real time, record and analyze the resource evaluation data, and generate a resource scheduling adjustment effect report including resource evaluation data, ecological impact assessment, and resource scheduling adjustment suggestions.

10. A digitalized fishing ground ecological chain intelligent scheduling system based on digital twinning, characterized in that, The following modules are included: An Internet of Things sensor module for collecting fishing field environment data in real time; A digital twin module for building and updating a digital twin virtual model of the fishing field in real time; A data analysis and algorithm optimization module for analyzing fishing field resource use data in the digital twin virtual model, and generating a resource scheduling optimization scheme in combination with a conjugate gradient algorithm; A simulation and ecological evaluation module for performing dynamic simulation on the resource scheduling optimization scheme, and generating a resource scheduling implementation scheme in combination with ecological evaluation results; A feedback control module for dynamically adjusting and optimizing the fishing field resource configuration in combination with a feedback control algorithm.

Images